Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
| en:vpet:mod:chatvpetprocess [2026/05/10 18:14] – [Table of Contents] 有米 | en:vpet:mod:chatvpetprocess [2026/05/10 23:23] (current) – 有米 | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | FIXME **This page is not fully translated, yet. Please help completing the translation.**\\ //(remove this paragraph once the translation is finished)// | ||
| - | |||
| # ChatVPet Process Setup Tutorial | # ChatVPet Process Setup Tutorial | ||
| Line 15: | Line 13: | ||
| - [What is Embedding](# | - [What is Embedding](# | ||
| - [Using OpenAI Embedding](# | - [Using OpenAI Embedding](# | ||
| - | - [Using | + | - [Using |
| 4. [Basic Settings — Other Parameters](# | 4. [Basic Settings — Other Parameters](# | ||
| 5. [Other Settings — Voice Input and Advanced Parameters](# | 5. [Other Settings — Voice Input and Advanced Parameters](# | ||
| - | 6. [知识库设置](#6-知识库设置) | + | 6. [Knowledge Base Settings](#6-Knowledge Base Settings) |
| - | 7. [数据库预览](#7-数据库预览) | + | 7. [Database Preview](#7-Database Preview) |
| - | 8. [常见问题](#8-常见问题) | + | 8. [FAQ](#8-FAQ) |
| --- | --- | ||
| Line 184: | Line 182: | ||
| | **Embedding URL** | The address of the Embedding endpoint; leave blank to use the primary API URL. | | | **Embedding URL** | The address of the Embedding endpoint; leave blank to use the primary API URL. | | ||
| | **Embedding Key** | The secret key for the Embedding endpoint; leave blank to automatically use the primary API Key. | | | **Embedding Key** | The secret key for the Embedding endpoint; leave blank to automatically use the primary API Key. | | ||
| - | | **Embedding Model** | The Embedding model to be used; defaults to `text-embedding-3-small`. | | + | | **Embedding Model** | The Embedding model to be used; defaults to `text-embedding-3-small` . | |
| <wrap info> **Note**：After changing the Embedding model or API, please go to the **Database Preview** tab and click **Clear Vector Cache** to ensure old cached data is invalidated and new vectors are regenerated. </ | <wrap info> **Note**：After changing the Embedding model or API, please go to the **Database Preview** tab and click **Clear Vector Cache** to ensure old cached data is invalidated and new vectors are regenerated. </ | ||
| - | --- | + | -- |
| + | - | ||
| ### 3.2 Using OpenAI Embedding | ### 3.2 Using OpenAI Embedding | ||
| Line 275: | Line 274: | ||
| **Rules**： | **Rules**： | ||
| - One piece of information per line | - One piece of information per line | ||
| + | |||
| - Knowledge is not directly loaded into the prompt in its entirety; instead, it is dynamically retrieved by the embedding algorithm based on relevance. | - Knowledge is not directly loaded into the prompt in its entirety; instead, it is dynamically retrieved by the embedding algorithm based on relevance. | ||
| + | |||
| - You can describe the Pet's persona, daily preferences, | - You can describe the Pet's persona, daily preferences, | ||
| + | |||
| - Use `{name}`to refer to the Pet's name and `{hostname}`to refer to the player' | - Use `{name}`to refer to the Pet's name and `{hostname}`to refer to the player' | ||
| + | |||
| - Changes will take effect after restarting the game. | - Changes will take effect after restarting the game. | ||
| Line 292: | Line 295: | ||
| --- | --- | ||
| - | |||
| ## 8. FAQ | ## 8. FAQ | ||
| Line 304: | Line 306: | ||
| **Q: Is configuring Embedding mandatory? ** | **Q: Is configuring Embedding mandatory? ** | ||
| + | |||
| A: Yes, it is mandatory. If you are unsure what to fill in, please refer to **3.3** | A: Yes, it is mandatory. If you are unsure what to fill in, please refer to **3.3** | ||
| + | |||
| **Q: Search results worsened after changing the Embedding model? ** | **Q: Search results worsened after changing the Embedding model? ** | ||
| + | |||
| A: Vectors generated by different models are incompatible. Please click **Clear Vector Cache** on the **Database Preview** page and wait for the vectors to be regenerated during the next conversation. | A: Vectors generated by different models are incompatible. Please click **Clear Vector Cache** on the **Database Preview** page and wait for the vectors to be regenerated during the next conversation. | ||
| + | |||
| **Q: How can I reduce Token consumption? | **Q: How can I reduce Token consumption? | ||
有米